# Understanding LLM Reasoning for Abstractive Summarization

arXiv: https://arxiv.org/abs/2512.03503 · HTML: https://mlsanity.com/paper/2512.03503/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 19 of its 73 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models](https://mlsanity.com/paper/2501.09686/) (2025)
- [WikiHow: A Large Scale Text Summarization Dataset](https://mlsanity.com/paper/1810.09305/) (2018)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents](https://mlsanity.com/paper/2508.02085/) (2025)
- [Curriculum-RLAIF: Curriculum Alignment with Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2505.20075/) (2025)
- [Semantic-Aware Logical Reasoning via a Semiotic Framework](https://mlsanity.com/paper/2509.24765/) (2025)
- [Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning](https://mlsanity.com/paper/2509.25300/) (2025)
- [AdaComp: Extractive Context Compression with Adaptive Predictor for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2409.01579/) (2024)
- [Context-Aware Hierarchical Merging for Long Document Summarization](https://mlsanity.com/paper/2502.00977/) (2025)
- [Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA](https://mlsanity.com/paper/2503.17933/) (2025)
- [StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMs](https://mlsanity.com/paper/2505.22950/) (2025)
- [ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback](https://mlsanity.com/paper/2503.21332/) (2025)
- [QA-prompting: Improving Summarization with Large Language Models using Question-Answering](https://mlsanity.com/paper/2505.14347/) (2025)
- [A Structure-aware Generative Model for Biomedical Event Extraction](https://mlsanity.com/paper/2408.06583/) (2024)

## Built on by (most cited first, 12 of 12)

- [TEMA: Anchor the Image, Follow the Text for Multi-Modification Composed Image Retrieval](https://mlsanity.com/paper/2604.21806/) (2026)
- [ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch](https://mlsanity.com/paper/2601.13606/) (2026)
- [ATTNPO: Attention-Guided Process Supervision for Efficient Reasoning](https://mlsanity.com/paper/2602.09953/) (2026)
- [FoE: Forest of Errors Makes the First Solution the Best in Large Reasoning Models](https://mlsanity.com/paper/2604.02967/) (2026)
- [Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.02993/) (2026)
- [ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing](https://mlsanity.com/paper/2604.11103/) (2026)
- [Beyond Output Correctness: Benchmarking and Evaluating Large Language Model Reasoning in Coding Tasks](https://mlsanity.com/paper/2604.12379/) (2026)
- [OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction](https://mlsanity.com/paper/2604.26252/) (2026)
- [A Large-Scale Multi-Dimensional Empirical Study of LLMs for Conversation Summarization](https://mlsanity.com/paper/2606.15974/) (2026)
- [LLMs Should Incorporate Explicit Mechanisms for Human Empathy](https://mlsanity.com/paper/2604.10557/) (2026)
- [HAVEN: Hierarchically Aligned Multimodal Benchmark for Unified Video Understanding](https://mlsanity.com/paper/2605.19223/) (2026)
- [VoxSumm: A Multilingual Corpus of Long-Form Spoken News for Joint Summarization and Translation](https://mlsanity.com/paper/2608.10359/) (2026)

## Abstract (arXiv)

Reasoning has substantially improved Large Language Models (LLMs) on analytical tasks such as mathematics and code generation, but its value for abstractive summarization remains unclear. To address this gap, we adapt general reasoning strategies to the summarization setting and conduct a large-scale comparative study of 8 reasoning strategies and 3 Large Reasoning Models (LRMs) across 8 diverse datasets, evaluating both summary quality and factual faithfulness. Our results show that reasoning is not a universal solution and its effectiveness depends strongly on the strategy and the summarization setting. In particular, we find a trade-off between summary quality and factual faithfulness. Explicit reasoning strategies often improve reference-based quality, but may weaken factual grounding, whereas implicit reasoning in LRMs shows the opposite tendency. We further find that increasing an LRM's internal reasoning budget does not reliably improve summarization and can even reduce factual consistency. These findings suggest that, for summarization, more reasoning is not always better. Effective reasoning should preserve faithful compression rather than induce over-elaboration. Our source code is publicly available.